In [19]:
from sklearn.decomposition import PCA
from sklearn.preprocessing import StandardScaler
X=np.zeros((len(days_kept)*len(mean_dico_tweet_state),3))
o=0
na=[]
emotion_list=["neutral/ambiguous","positive","negative"]
for s in mean_dico_tweet_state.keys():
for d in days_kept:
na.append(s+'_'+d)
X[o][0]=mean_dico_tweet_state[s][d]['neutral/ambiguous']
X[o][1]=mean_dico_tweet_state[s][d]['positive']
X[o][2]=mean_dico_tweet_state[s][d]['negative']
o+=1
df_temp=pd.DataFrame([[X[i,0],X[i,1],X[i,2]] for i in range(len(X))],columns=emotion_list,index=na)
#scaler = StandardScaler() #define the scaler object
#scaler.fit(df_temp)
#scaled_data = scaler.transform(df_temp)
scaled_data = df_temp
pca = PCA()#create a PCA object
pca.fit(scaled_data)#calculate the eigenvalues and eigenvectors according to rescaled data
x_pca = pca.transform(scaled_data)# Calculate the new points coordinate according to the previously found eigenvectors.
var_explained=pca.explained_variance_ratio_
fig, ax = plt.subplots(figsize = (8,8))
ax.scatter(x_pca[:,0],x_pca[:,1])
feature_vectors = pca.components_.T
#Going from the feature base to the PCA base is easy : one is just the other transposed.
# we use scaling factors to make the arrows easier to see
arrow_size, text_pos = 0.1,0.1,
# projections of the original features
for i, v in enumerate(feature_vectors):
ax.arrow(0, 0, arrow_size*v[0], arrow_size*v[1],head_width=0.02, head_length=0.02, linewidth=2, color='red')
ax.text(v[0]*text_pos, v[1]*text_pos, df_temp.columns[i], color='black',ha='left', va='top', fontsize=18)
plt.title('Not Scaled')
plt.xlabel('First Principal Component,\n var explained = {0:.2f}'.format(var_explained[0]))
plt.ylabel('Second Principal Component,\n var explained = {0:.2f}'.format(var_explained[1]))
plt.show()
